{"id":"W4409576520","doi":"10.61091/jcmcc127a-145","title":"A Study of Modeling Algorithm Improvement for Semantic Analysis of Public English Texts","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Educational Systems and Policies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Semantic analysis (machine learning); Artificial intelligence; Algorithm","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01404087,0.001092852,0.001199273,0.001686814,0.0009764484,0.002648772,0.001924075,0.001177688,0.001481562],"category_scores_gemma":[0.0809202,0.0004907278,0.001253778,0.002215606,0.001069764,0.007775582,0.001253987,0.002319602,0.0005095874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002193362,"about_ca_system_score_gemma":0.002205795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006722772,"about_ca_topic_score_gemma":0.003044751,"domain_scores_codex":[0.9888665,0.006579858,0.0005629645,0.001975433,0.001704202,0.000311024],"domain_scores_gemma":[0.9445779,0.04064304,0.001889201,0.006321668,0.006304591,0.0002635436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006873122,0.000771946,0.02063858,0.0005207166,0.0003908031,0.0001699902,0.002493522,0.2337021,0.01308563,0.06282204,0.0045643,0.660153],"study_design_scores_gemma":[0.00001728239,0.0001253084,0.001505475,0.00002567489,0.00005427129,0.00006585534,0.0002192025,0.9816875,0.005359366,0.008678803,0.002243479,0.00001774624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1229301,0.001047794,0.8697173,0.0008782183,0.0001021959,0.0001276526,0.00007574573,0.001841034,0.003279905],"genre_scores_gemma":[0.5665717,0.0004648016,0.430475,0.0001708257,0.00007152947,0.0001651931,0.0003787498,0.0004324629,0.001269686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01404087,"threshold_uncertainty_score":0.07425612,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02292818587694894,"score_gpt":0.2943475408140213,"score_spread":0.2714193549370723,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}